The bot couldn't answer it. Neither could I.
I read the question my support bot had fluffed, gave the correct answer off the top of my head, and was wrong. The docs had fooled the person who wrote them.

I read the question my support bot had fluffed, gave the correct answer off the top of my head, and was wrong. The docs had fooled the person who wrote them.

Whenever I explain that phpbotscout answers from the estate’s documentation, somebody asks why it doesn’t read the issues as well, and it’s a fair question. They’re right there, they’re full of questions shaped exactly …

Go says a constructor either works or it doesn't. That contract stops making sense the moment a client has a dozen optional parts, so I broke it on purpose.

A soft launch for Scout, an AI co-dungeon-master for long tabletop campaigns, and why it will never speak to the players.

A model in an internal evaluation did something nobody asked it to do, and the interesting part is what that does and does not prove.

Building an AI dungeon master to test a Go chat client, and the bug that kept resurrecting a goblin the player had definitively killed.

Build an AI dungeon master in Go: keep the model to prose only by putting the rules in the system prompt and the mechanics in typed tool calls.
